import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
import seaborn as sns

from wordcloud import WordCloud
import plotly.express as px
import plotly.graph_objects as go

%matplotlib inline
sns.set_style('whitegrid')

This is basic data analysis on covid-19 vaccination drive that is undergoing around the world. As world has been facing serious pandemic from many months, many countries have successfully developed effective vaccine against this pandemic.

The data here is the record of the vaccination drive around the world. It is started from 2020-12-13 and captures the data up to 2021-03-10

df = pd.read_csv('country_vaccinations.csv')

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5824 entries, 0 to 5823
Data columns (total 15 columns):
 #   Column                               Non-Null Count  Dtype  
---  ------                               --------------  -----  
 0   country                              5824 non-null   object 
 1   iso_code                             5476 non-null   object 
 2   date                                 5824 non-null   object 
 3   total_vaccinations                   3717 non-null   float64
 4   people_vaccinated                    3302 non-null   float64
 5   people_fully_vaccinated              2257 non-null   float64
 6   daily_vaccinations_raw               3131 non-null   float64
 7   daily_vaccinations                   5637 non-null   float64
 8   total_vaccinations_per_hundred       3717 non-null   float64
 9   people_vaccinated_per_hundred        3302 non-null   float64
 10  people_fully_vaccinated_per_hundred  2257 non-null   float64
 11  daily_vaccinations_per_million       5637 non-null   float64
 12  vaccines                             5824 non-null   object 
 13  source_name                          5824 non-null   object 
 14  source_website                       5824 non-null   object 
dtypes: float64(9), object(6)
memory usage: 682.6+ KB

df[['date']].tail()

	date
5819	2021-03-06
5820	2021-03-07
5821	2021-03-08
5822	2021-03-09
5823	2021-03-10

# This much null value is present in dataset
df.isna().sum()

country                                   0
iso_code                                348
date                                      0
total_vaccinations                     2107
people_vaccinated                      2522
people_fully_vaccinated                3567
daily_vaccinations_raw                 2693
daily_vaccinations                      187
total_vaccinations_per_hundred         2107
people_vaccinated_per_hundred          2522
people_fully_vaccinated_per_hundred    3567
daily_vaccinations_per_million          187
vaccines                                  0
source_name                               0
source_website                            0
dtype: int64

It may happen because not every country is started vaccination or not record is maintaning properly. It is also possible that the data we are using is incomplet or some other reasons. However, we have the data and anaysis will happen on it.

Data Cleaning

IN this section what we done primarly is-

## will replace null value with 0 assuming that there is no data available for that column or nothing has happend regarding that particular column.
## convert all the numeric values from object type to numeric type
## Convert date from object to datetime data type
## add three new column year, month, days

df.fillna(0, inplace=True)
df.head()

	country	iso_code	date	total_vaccinations	people_vaccinated	people_fully_vaccinated	daily_vaccinations_raw	daily_vaccinations	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	daily_vaccinations_per_million	vaccines	source_name	source_website
0	Albania	ALB	2021-01-10	0.0	0.0	0.0	0.0	0.0	0.00	0.00	0.0	0.0	Pfizer/BioNTech	Ministry of Health	https://shendetesia.gov.al/covid19-ministria-e...
1	Albania	ALB	2021-01-11	0.0	0.0	0.0	0.0	64.0	0.00	0.00	0.0	22.0	Pfizer/BioNTech	Ministry of Health	https://shendetesia.gov.al/covid19-ministria-e...
2	Albania	ALB	2021-01-12	128.0	128.0	0.0	0.0	64.0	0.00	0.00	0.0	22.0	Pfizer/BioNTech	Ministry of Health	https://shendetesia.gov.al/covid19-ministria-e...
3	Albania	ALB	2021-01-13	188.0	188.0	0.0	60.0	63.0	0.01	0.01	0.0	22.0	Pfizer/BioNTech	Ministry of Health	https://shendetesia.gov.al/covid19-ministria-e...
4	Albania	ALB	2021-01-14	266.0	266.0	0.0	78.0	66.0	0.01	0.01	0.0	23.0	Pfizer/BioNTech	Ministry of Health	https://shendetesia.gov.al/covid19-ministria-e...

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5824 entries, 0 to 5823
Data columns (total 15 columns):
 #   Column                               Non-Null Count  Dtype  
---  ------                               --------------  -----  
 0   country                              5824 non-null   object 
 1   iso_code                             5824 non-null   object 
 2   date                                 5824 non-null   object 
 3   total_vaccinations                   5824 non-null   float64
 4   people_vaccinated                    5824 non-null   float64
 5   people_fully_vaccinated              5824 non-null   float64
 6   daily_vaccinations_raw               5824 non-null   float64
 7   daily_vaccinations                   5824 non-null   float64
 8   total_vaccinations_per_hundred       5824 non-null   float64
 9   people_vaccinated_per_hundred        5824 non-null   float64
 10  people_fully_vaccinated_per_hundred  5824 non-null   float64
 11  daily_vaccinations_per_million       5824 non-null   float64
 12  vaccines                             5824 non-null   object 
 13  source_name                          5824 non-null   object 
 14  source_website                       5824 non-null   object 
dtypes: float64(9), object(6)
memory usage: 682.6+ KB

df.total_vaccinations = df.total_vaccinations.astype(int)
df.people_vaccinated = df.people_vaccinated.astype(int)
df.people_fully_vaccinated = df.people_fully_vaccinated.astype(int)
df.daily_vaccinations_raw = df.daily_vaccinations_raw.astype(int)
df.daily_vaccinations = df.daily_vaccinations.astype(int)
df.total_vaccinations_per_hundred = df.total_vaccinations_per_hundred.astype(int)
df.people_vaccinated_per_hundred = df.people_vaccinated_per_hundred.astype(int)
df.people_fully_vaccinated_per_hundred = df.people_fully_vaccinated_per_hundred.astype(int)
df.daily_vaccinations_per_million = df.daily_vaccinations_per_million.astype(int)

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5824 entries, 0 to 5823
Data columns (total 15 columns):
 #   Column                               Non-Null Count  Dtype 
---  ------                               --------------  ----- 
 0   country                              5824 non-null   object
 1   iso_code                             5824 non-null   object
 2   date                                 5824 non-null   object
 3   total_vaccinations                   5824 non-null   int64 
 4   people_vaccinated                    5824 non-null   int64 
 5   people_fully_vaccinated              5824 non-null   int64 
 6   daily_vaccinations_raw               5824 non-null   int64 
 7   daily_vaccinations                   5824 non-null   int64 
 8   total_vaccinations_per_hundred       5824 non-null   int64 
 9   people_vaccinated_per_hundred        5824 non-null   int64 
 10  people_fully_vaccinated_per_hundred  5824 non-null   int64 
 11  daily_vaccinations_per_million       5824 non-null   int64 
 12  vaccines                             5824 non-null   object
 13  source_name                          5824 non-null   object
 14  source_website                       5824 non-null   object
dtypes: int64(9), object(6)
memory usage: 682.6+ KB

date = df.date.str.split('-', expand=True)
date

	0	1	2
0	2021	01	10
1	2021	01	11
2	2021	01	12
3	2021	01	13
4	2021	01	14
...	...	...	...
5819	2021	03	06
5820	2021	03	07
5821	2021	03	08
5822	2021	03	09
5823	2021	03	10

5824 rows × 3 columns

df['year'] = date[0]
df['month']=date[1]
df['day']=date[2]

df.year = df.year.astype(int)
df.month=df.month.astype(int)
df.day = pd.to_numeric(df.day)

df.date = pd.to_datetime(df.date)

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5824 entries, 0 to 5823
Data columns (total 18 columns):
 #   Column                               Non-Null Count  Dtype         
---  ------                               --------------  -----         
 0   country                              5824 non-null   object        
 1   iso_code                             5824 non-null   object        
 2   date                                 5824 non-null   datetime64[ns]
 3   total_vaccinations                   5824 non-null   int64         
 4   people_vaccinated                    5824 non-null   int64         
 5   people_fully_vaccinated              5824 non-null   int64         
 6   daily_vaccinations_raw               5824 non-null   int64         
 7   daily_vaccinations                   5824 non-null   int64         
 8   total_vaccinations_per_hundred       5824 non-null   int64         
 9   people_vaccinated_per_hundred        5824 non-null   int64         
 10  people_fully_vaccinated_per_hundred  5824 non-null   int64         
 11  daily_vaccinations_per_million       5824 non-null   int64         
 12  vaccines                             5824 non-null   object        
 13  source_name                          5824 non-null   object        
 14  source_website                       5824 non-null   object        
 15  year                                 5824 non-null   int64         
 16  month                                5824 non-null   int64         
 17  day                                  5824 non-null   int64         
dtypes: datetime64[ns](1), int64(12), object(5)
memory usage: 819.1+ KB

# Finally Some highlights of dataset
print('Number of countries participated in vaccinations: ',len(df.country.unique()))
print('Date at which the vaccination started',df.date.min())
print('Data points ends at the date: ',df.date.max())
print('Nunber of vaccines are in use: ',len(df.vaccines.unique()))

Number of countries participated in vaccinations:  130
Date at which the vaccination started 2020-12-13 00:00:00
Data points ends at the date:  2021-03-10 00:00:00
Nunber of vaccines are in use:  24

df.describe().transpose()

	count	mean	std	min	25%	50%	75%	max
total_vaccinations	5824.0	1.336148e+06	5.840887e+06	0.0	0.0	26512.5	466527.50	95721290.0
people_vaccinated	5824.0	9.815566e+05	4.198054e+06	0.0	0.0	10690.0	294756.50	62451150.0
people_fully_vaccinated	5824.0	2.534459e+05	1.650972e+06	0.0	0.0	0.0	30394.75	32904161.0
daily_vaccinations_raw	5824.0	4.407231e+04	1.785066e+05	0.0	0.0	327.5	15335.75	2904229.0
daily_vaccinations	5824.0	5.634211e+04	1.850083e+05	0.0	1034.0	5921.0	27478.00	2169981.0
total_vaccinations_per_hundred	5824.0	5.057005e+00	1.286193e+01	0.0	0.0	0.0	4.00	133.0
people_vaccinated_per_hundred	5824.0	3.472184e+00	8.577710e+00	0.0	0.0	0.0	3.00	85.0
people_fully_vaccinated_per_hundred	5824.0	9.344093e-01	4.143049e+00	0.0	0.0	0.0	0.00	47.0
daily_vaccinations_per_million	5824.0	2.460897e+03	4.297707e+03	0.0	310.0	1127.0	2561.50	54264.0
year	5824.0	2.020943e+03	2.318730e-01	2020.0	2021.0	2021.0	2021.00	2021.0
month	5824.0	2.389423e+00	2.456588e+00	1.0	1.0	2.0	2.00	12.0
day	5824.0	1.503898e+01	9.010347e+00	1.0	7.0	15.0	23.00	31.0

df.country.unique()

array(['Albania', 'Algeria', 'Andorra', 'Anguilla', 'Argentina',
       'Australia', 'Austria', 'Azerbaijan', 'Bahrain', 'Bangladesh',
       'Barbados', 'Belarus', 'Belgium', 'Belize', 'Bermuda', 'Bolivia',
       'Brazil', 'Bulgaria', 'Cambodia', 'Canada', 'Cayman Islands',
       'Chile', 'China', 'Colombia', 'Costa Rica', 'Croatia', 'Cyprus',
       'Czechia', 'Denmark', 'Dominica', 'Dominican Republic', 'Ecuador',
       'Egypt', 'El Salvador', 'England', 'Estonia', 'Faeroe Islands',
       'Falkland Islands', 'Finland', 'France', 'Germany', 'Ghana',
       'Gibraltar', 'Greece', 'Greenland', 'Grenada', 'Guatemala',
       'Guernsey', 'Guyana', 'Honduras', 'Hong Kong', 'Hungary',
       'Iceland', 'India', 'Indonesia', 'Iran', 'Ireland', 'Isle of Man',
       'Israel', 'Italy', 'Japan', 'Jersey', 'Jordan', 'Kazakhstan',
       'Kuwait', 'Latvia', 'Lebanon', 'Liechtenstein', 'Lithuania',
       'Luxembourg', 'Macao', 'Malaysia', 'Maldives', 'Malta',
       'Mauritius', 'Mexico', 'Moldova', 'Monaco', 'Mongolia',
       'Montenegro', 'Montserrat', 'Morocco', 'Myanmar', 'Nepal',
       'Netherlands', 'New Zealand', 'Northern Cyprus',
       'Northern Ireland', 'Norway', 'Oman', 'Pakistan', 'Panama',
       'Paraguay', 'Peru', 'Philippines', 'Poland', 'Portugal', 'Qatar',
       'Romania', 'Russia', 'Rwanda', 'Saint Helena', 'Saint Lucia',
       'San Marino', 'Saudi Arabia', 'Scotland', 'Senegal', 'Serbia',
       'Seychelles', 'Singapore', 'Slovakia', 'Slovenia', 'South Africa',
       'South Korea', 'Spain', 'Sri Lanka', 'Sweden', 'Switzerland',
       'Thailand', 'Trinidad and Tobago', 'Turkey',
       'Turks and Caicos Islands', 'Ukraine', 'United Arab Emirates',
       'United Kingdom', 'United States', 'Uruguay', 'Venezuela', 'Wales',
       'Zimbabwe'], dtype=object)

wordCloud = WordCloud(background_color='white',max_font_size=50).generate(' '.join(df.country))
plt.figure(figsize=(15,7))
plt.axis('off')
plt.imshow(wordCloud)
plt.show()

Total Vaccination Till 12-March 2021

country_wise_total_vaccinated = {}
for country in df.country.unique():
    vaccinated = 0
    for i in range(len(df)):
        if df.country[i]==country:
            vaccinated += df.daily_vaccinations[i]
    country_wise_total_vaccinated[country]=vaccinated
country_wise_total_vaccinated_df = pd.DataFrame.from_dict(country_wise_total_vaccinated, orient='index',
                                               columns=['total_vaccinated_till_date'])
country_wise_total_vaccinated_df.sort_values(by='total_vaccinated_till_date',ascending=False, inplace=True)
country_wise_total_vaccinated_df

	total_vaccinated_till_date
United States	89468175
China	49687760
United Kingdom	23297315
India	22256015
England	19639663
...	...
Montserrat	645
Trinidad and Tobago	441
Grenada	145
Honduras	0
Saint Helena	0

130 rows × 1 columns

fig = px.bar(country_wise_total_vaccinated_df,
            y='total_vaccinated_till_date',
            x=country_wise_total_vaccinated_df.index,
            color='total_vaccinated_till_date',
            color_discrete_sequence=px.colors.sequential.Viridis_r
            )
fig.update_layout(
    title={
        'text':'Vaccination till date in various countries',
        'y':0.95,
        'x':0.5
    },
    xaxis_title='Countries',
    yaxis_title='Total Vaccinated',
    legend_title='Total Vaccinated'
)
fig.show()

From the plot Top list of in total vaccinated people country

US

China

UK

India

# Countrywise daily vaccination
fig = px.line(df, x='date', y='daily_vaccinations',color='country')
fig.update_layout(
    title={
        'text':'Daily Vaccination trend',
        'y':0.95,
        'x':0.5
    },
    xaxis_title='Date',
    yaxis_title='Daily Vaccinations'
)
fig.show()

def plot_till_date(value1, value2, title, color1, color2):
    so_far_dict = {}
    
    for dates in df.date.unique():
        so_far_dict[dates],value1_count,value2_count=[],0,0
        
        for i in range(len(df)):
            if df.date[i]==dates:
                value1_count+=df[value1][i]
                value2_count+=df[value2][i]
        so_far_dict[dates].append(value1_count)
        so_far_dict[dates].append(value2_count)
    so_far_df = pd.DataFrame.from_dict(so_far_dict, orient='index',columns=[value1, value2])
    so_far_df.reset_index(inplace=True)
    
    so_far_df.sort_values(by='index',inplace=True)
    plot = go.Figure(data=[go.Scatter(
        x = so_far_df['index'],
        y = so_far_df[value1],
        stackgroup='one',
        name = value1,
        marker_color=color1
    ),
                          
        go.Scatter(
        x = so_far_df['index'],
        y = so_far_df[value2],
            stackgroup = 'one',
            name=value2,
            marker_color=color2
        )])
    
    plot.update_layout(
        title={
            'text':title,
            'y': 0.95,
            'x':0.5
        },
        xaxis_title='Date'
    )
    display(so_far_df.head(5))
    return plot.show()

plot_till_date('people_fully_vaccinated','people_vaccinated','People vaccinated vs fully vaccinated till date',
              '#c4eb28','#35eb28')

	index	people_fully_vaccinated	people_vaccinated
87	2020-12-13	0	172930
78	2020-12-14	0	0
79	2020-12-15	0	28500
80	2020-12-16	0	0
81	2020-12-17	0	0

plot_till_date('people_fully_vaccinated_per_hundred','people_vaccinated_per_hundred',
               'People vaccinated vs fully vaccinated per hundred till date','#0938e3','#7127cc')

	index	people_fully_vaccinated_per_hundred	people_vaccinated_per_hundred
87	2020-12-13	0	0
78	2020-12-14	0	0
79	2020-12-15	0	0
80	2020-12-16	0	0
81	2020-12-17	0	0

# Pie Plot
def plot_pie(value, title, color):
    new_dict = {}
    for v in df[value].unique():
        value_count=0
        for i in range(len(df)):
            if df[value][i]==v:
                value_count+=1
        new_dict[v]=value_count
    print(new_dict)
    new_df = pd.DataFrame.from_dict(new_dict, orient='index',columns=['Total'])
    
    if color=='plasma':
        fig = px.pie(new_df, values='Total',
                    names = new_df.index,
                    title = title,
                    color_discrete_sequence=px.colors.sequential.Plasma)
    elif color=='rainbow':
        fig = px.pie(new_df, values='Total',
                    names = new_df.index,
                    title = title,
                    color_discrete_sequence=px.colors.sequential.Rainbow)
    else:
        fig = px.pie(new_df, values='Total',
                    names=new_df.index,
                    title=title)
    fig.update_layout(
        title={
            'x':0.5,
            'y':0.95
        },
        legend_title = value
    )
    return fig.show()

most used vaccine

df.vaccines.unique()

array(['Pfizer/BioNTech', 'Sputnik V', 'Oxford/AstraZeneca',
       'Oxford/AstraZeneca, Sinopharm/Beijing, Sputnik V',
       'Oxford/AstraZeneca, Pfizer/BioNTech',
       'Moderna, Oxford/AstraZeneca, Pfizer/BioNTech', 'Sinovac',
       'Oxford/AstraZeneca, Pfizer/BioNTech, Sinopharm/Beijing, Sputnik V',
       'Oxford/AstraZeneca, Sinovac', 'Sinopharm/Beijing',
       'Moderna, Pfizer/BioNTech', 'Pfizer/BioNTech, Sinovac',
       'Sinopharm/Beijing, Sinopharm/Wuhan, Sinovac', 'Moderna',
       'Moderna, Oxford/AstraZeneca, Pfizer/BioNTech, Sinopharm/Beijing, Sputnik V',
       'Covaxin, Oxford/AstraZeneca',
       'Pfizer/BioNTech, Sinopharm/Beijing',
       'Oxford/AstraZeneca, Pfizer/BioNTech, Sputnik V',
       'Sinopharm/Beijing, Sputnik V',
       'Oxford/AstraZeneca, Sinopharm/Beijing', 'EpiVacCorona, Sputnik V',
       'Johnson&Johnson',
       'Oxford/AstraZeneca, Pfizer/BioNTech, Sinopharm/Beijing, Sinopharm/Wuhan, Sputnik V',
       'Johnson&Johnson, Moderna, Pfizer/BioNTech'], dtype=object)

plot_pie('vaccines','Various vaccines and their uses','plasma')

{'Pfizer/BioNTech': 1095, 'Sputnik V': 197, 'Oxford/AstraZeneca': 400, 'Oxford/AstraZeneca, Sinopharm/Beijing, Sputnik V': 92, 'Oxford/AstraZeneca, Pfizer/BioNTech': 842, 'Moderna, Oxford/AstraZeneca, Pfizer/BioNTech': 1508, 'Sinovac': 193, 'Oxford/AstraZeneca, Pfizer/BioNTech, Sinopharm/Beijing, Sputnik V': 140, 'Oxford/AstraZeneca, Sinovac': 54, 'Sinopharm/Beijing': 114, 'Moderna, Pfizer/BioNTech': 358, 'Pfizer/BioNTech, Sinovac': 126, 'Sinopharm/Beijing, Sinopharm/Wuhan, Sinovac': 76, 'Moderna': 6, 'Moderna, Oxford/AstraZeneca, Pfizer/BioNTech, Sinopharm/Beijing, Sputnik V': 73, 'Covaxin, Oxford/AstraZeneca': 55, 'Pfizer/BioNTech, Sinopharm/Beijing': 45, 'Oxford/AstraZeneca, Pfizer/BioNTech, Sputnik V': 77, 'Sinopharm/Beijing, Sputnik V': 17, 'Oxford/AstraZeneca, Sinopharm/Beijing': 102, 'EpiVacCorona, Sputnik V': 86, 'Johnson&Johnson': 23, 'Oxford/AstraZeneca, Pfizer/BioNTech, Sinopharm/Beijing, Sinopharm/Wuhan, Sputnik V': 64, 'Johnson&Johnson, Moderna, Pfizer/BioNTech': 81}

plot_pie('source_name','Sources','plasma')

{'Ministry of Health': 1791, 'Government of Andorra': 33, 'Government of Australia via covidlive.com.au': 24, 'Government of Azerbaijan': 53, 'Directorate General of Health Services': 43, 'Sciensano': 72, 'Government of Bermuda': 53, 'Regional governments via Coronavirus Brasil': 54, 'Official data from provinces via covid19tracker.ca': 87, 'Cayman Islands Government': 70, 'Department of Statistics and Health Information': 77, 'National Health Commission': 148, 'Government of Cyprus': 59, 'Statens Serum Institut': 74, 'Government of Dominica': 19, 'Ministry of Public Health': 24, 'Government of Ecuador via Ecuacovid': 48, 'Government of the United Kingdom': 435, 'National Health Board': 73, 'Government of the Faeroe Islands': 39, 'Government of the Falkland Islands': 16, 'Finnish Institute for Health and Welfare': 70, 'Public Health France': 73, 'Robert Koch Institut': 74, 'Government of Ghana': 10, 'Government of Gibraltar': 60, 'Government of Greenland': 34, 'Government of Grenada': 6, 'Government of Guernsey': 38, 'Government of Honduras': 1, 'Government of Hong Kong': 18, 'Government of Hungary': 73, 'Directorate of Health': 69, 'Government of Iran': 10, 'Heath Service Executive': 67, 'Isle of Man Government': 49, 'Government of Israel': 82, 'Extraordinary commissioner for the Covid-19 emergency': 74, 'Ministry of Health, Labour and Welfare': 22, 'Government of Jersey': 36, 'Government of Jordan': 45, 'Government of Kazakhstan': 25, 'National Health Service': 69, 'Government of Lebanon': 26, 'Federal Office of Public Health': 76, 'Government of Luxembourg': 70, 'Government of Macao': 11, 'Government of Malaysia': 15, 'Presidency of the Maldives': 37, 'COVID-19 Malta Public Health Response Team': 52, 'National Communication Committee on COVID-19': 24, 'Secretary of Health': 77, 'National Council': 20, 'Government of Montenegro': 17, 'Government of Montserrat': 16, 'Government of Nepal': 26, 'National Institute for Public Health and the Environment': 50, 'Norwegian Institute of Public Health': 73, 'National Command and Operation Centre': 20, 'Government of Paraguay': 18, 'Government of the Philippines': 9, 'General Directorate of Health via Data Science for Social Good': 74, 'National Strategic Group on COVID-19': 76, 'Government of Romania': 73, 'Official data from local governments via gogov.ru': 86, 'Government of Saint Helena': 1, 'Social Security Institute': 11, 'Saudi Health Council': 64, 'Government of Serbia': 62, 'Extended Programme for Immunisation': 60, 'National Institute of Public Health, via Sledilnik': 73, 'Korea Centers for Disease Control and Prevention': 14, 'Public Health Agency of Sweden': 74, 'Government of Thailand': 4, 'COVID-19 Vaccine Information Platform': 57, 'National Emergency Crisis and Disaster Management Authority': 64, 'Centers for Disease Control and Prevention': 81, 'Government of Venezuela': 16}

wordCloud = WordCloud(background_color='white',
                     max_font_size=50).generate(' '.join(df.vaccines))
plt.figure(figsize=(12,5))
plt.axis('off')
plt.imshow(wordCloud)
plt.show()

# Daily vaccination trend per million

fig = px.line(df, x='date',y='daily_vaccinations_per_million', color='country')
fig.update_layout(
    title={
        'text':'Daily vaccination trend per million',
        'x':0.5,
        'y':0.95
    },
    xaxis_title='Date',
    yaxis_title='Daily Vaccinations per million'
)
fig.show()

Total Vaccinated - India vs USA

india_usa = [df[df.country=='India'], df[df.country=='United States']]
result = pd.concat(india_usa)

fig = px.line(result, x='date',y='total_vaccinations',color='country')
fig.update_layout(
    title={
        'text':'Total Vaccinated-India vs United States',
        'x':0.5,
        'y':0.95
    },
    xaxis_title = 'Date',
    yaxis_title = 'Total Vaccinations'
)
fig.show()

def plot_map(variable, title, color):
    
    new_dict = {}
    for country in df.country.unique():
        for i in range(len(df)):
            if df.country[i]==country:
                new_dict[country]=df[variable][i]
    new_dict
    
    new_df = pd.DataFrame.from_dict(new_dict,orient='index',columns=[variable])
    
    if color==None:
        place_map = px.choropleth(new_df, locations=new_df.index,
                                 locationmode='country names',
                                 color=variable,
                                 hover_name=new_df.index)
    else:
        place_map = px.choropleth(new_df, locations=new_df.index,
                                 locationmode='country names',
                                 color=variable,
                                 hover_name = new_df.index,
                                 color_continuous_scale=color)
    place_map.update_layout(
        title_text = title,
        title_x = 0.5,
        geo = dict(showocean=True, oceancolor='#7af8ff',
                  showland=True, landcolor='white',
                  showframe=False)
    )
    return place_map.show()

plot_map('total_vaccinations','Most Vaccinated country', None)

plot_map('vaccines','Vaccines Used in Different countries', None)

plot_map('people_fully_vaccinated','People fully vaccinated in Different countries','haline')

def plot_animation(value, title, color):
    new_df = df[df.year==2021]
    new_df.sort_values(by='day',inplace=True)
    if color==None:
        place_map = px.choropleth(new_df, locations='country',
                                 locationmode='country names',
                                 color=value,
                                 hover_name='country',
                                 animation_frame='day')
    else:
        place_map = px.choropleth(new_df, locations='country',
                                 locationmode='country names',
                                 color=value,
                                 hover_name='country',
                                 animation_frame='day',
                                 color_continuous_scale=color)
    place_map.update_layout(
        title_text = title,
        title_x = 0.5,
        geo = dict(showocean=True, oceancolor='#7af8ff',
                  showland=True, landcolor='white',
                  showframe=False)
    )
    return place_map.show()

plot_animation('daily_vaccinations','Animation of daily vaccinations through January 2021 in different countries',None)

<ipython-input-39-1001565589c3>:3: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

plot_animation('daily_vaccinations_per_million','Animation of daily Vaccinations per million through january 2021 in different countries','Plotly3')

<ipython-input-39-1001565589c3>:3: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

3D scatter_3d

fig = px.scatter_3d(df.head(500), x='date', y='people_vaccinated', z='people_fully_vaccinated',
                   color='country',hover_data=['country'],
                   size='people_fully_vaccinated',
                   opacity=0.9,
                   symbol='country')
fig.update_layout(title='Date vs People vaccinated vs People Fully Vaccinated|3D')
fig.update_layout(title={
    'y':0.95,
    'x':0.5
})
fig.show()

def size(m,n):
    fig = plt.gcf()
    fig.set_size_inches(m,n)

sns.heatmap(df.corr())
plt.title('Corelation Heatmap')
plt.yticks(rotation=0)
size(10,7)